AI agents call load_data to retrieve information from ParaView-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads data from files and loads it into ParaView for visualization. It has no side effects beyond making data available in memory for analysis. While file I/O operations could pose security risks if paths are not validated, the core function is data retrieval rather than creation, modification, deletion, code execution, or financial operations.
From the tool's definition Tool name 'load_data' and description 'Load data from a file into ParaView' indicate reading/importing data from storage into the application. The action is non-destructive—it retrieves existing data without modification.
Documented attack patterns abuse exactly the kind of access load_data gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ParaView-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for load_data:
{
"version": "1",
"default": "deny",
"tools": {
"load_data": {}
}
}load_data is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Load data from a file into ParaView. It is categorised as a Read tool in the ParaView-MCP MCP Server, which means it retrieves data without modifying state.
Register the ParaView- MCP server in PolicyLayer and add a rule for load_data: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches ParaView-MCP. Nothing to install.
load_data is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the load_data rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for load_data. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
load_data is provided by the ParaView- MCP server (llnl/paraview_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ParaView-MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
23 ParaView-MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.